alexeytochin/tf_seq2seq_losses
TensorFlow implementations of losses for sequence to sequence machine learning models
This is a TensorFlow library that significantly speeds up the calculation of Connectionist Temporal Classification (CTC) loss functions, which are critical for training machine learning models on sequential data. It takes in model output logits and ground truth labels, and outputs a more accurate and stable loss value much faster than standard TensorFlow. This tool is designed for machine learning engineers and researchers working on sequence-to-sequence problems.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher building models for speech recognition, handwriting recognition, or other sequence-to-sequence tasks and need faster training or stable second-order derivatives for your CTC loss calculations.
Not ideal if you are not working with TensorFlow or if your machine learning problem does not involve sequence-to-sequence modeling with CTC loss.
Stars
10
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alexeytochin/tf_seq2seq_losses"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
facebookresearch/fairseq2
FAIR Sequence Modeling Toolkit 2
lhotse-speech/lhotse
Tools for handling multimodal data in machine learning projects.
google/sequence-layers
A neural network layer API and library for sequence modeling, designed for easy creation of...
awslabs/sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
OpenNMT/OpenNMT-tf
Neural machine translation and sequence learning using TensorFlow